Fast and Accurate Multiclass Inference for MI-BCIs Using Large Multiscale Temporal and Spectral Features
TL
TL;DR
This work focuses on the well-known common spatial pattern (CSP) and Riemannian covariance methods, and significantly extend these two feature extractors to multiscale temporal and spectral cases.
Abstract
Accurate, fast, and reliable multiclass classification of electroencephalography (EEG) signals is a challenging task towards the development of motor imagery brain-computer interface (MI-BCI) systems. We propose enhancements to different feature extractors, along with a support vector machine (SVM) classifier, to simultaneously improve classification accuracy and execution time during training and testing. We focus on the well-known common spatial pattern (CSP) and Riemannian covariance methods, and significantly extend these two feature extractors to multiscale temporal and spectral cases. The multiscale CSP features achieve $\pmb{73.70\pm15.90\%} (\mathbf{mean}\pm$ standard deviation across 9 subjects) classification accuracy that surpasses the state-of-the-art method [1], $\pmb{70.6\pm 14.70\%}$, on the 4-class BCI competition IV-2a dataset. The Riemannian covariance features outperform the CSP by achieving $\pmb{74.27\pm15.5\%}$ accuracy and executing 9x faster in training and 4x faster in testing. Using more temporal windows for Riemannian features results in $\pmb{75.47\pm 12.8\%}$ accuracy with 1.6x faster testing than CSP.
References13 items
1
EEG feature descriptors and discriminant analysis under Riemannian Manifold perspective
2
Riemannian Approaches in Brain-Computer Interfaces: A Review
3
On the use of convolutional neural networks and augmented CSP features for multi-class motor imagery of EEG signals classification
4
Parallel convolutional-linear neural network for motor imagery classification
5